© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128672
    Prev
    Next
    INDEX
    Explanations

    The neuron flags numeric literals (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    assignment or comparison equals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     termurah
    -1.25
     któ
    -1.24
     étudiant
    -1.23
    ᥫ
    -1.22
    uated
    -1.21
     polecam
    -1.18
     barato
    -1.17
    Kommentare
    -1.17
     hà
    -1.16
    passion
    -1.16
    POSITIVE LOGITS
     is
    1.14
     while
    1.13
     de
    1.13
     when
    1.02
     for
    0.96
     l
    0.96
     подготовка
    0.95
    热水
    0.93
     del
    0.92
    だからこそ
    0.92
    Activations Density 0.020%

    No Known Activations